© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11109
    Prev
    Next
    INDEX
    Explanations

    negative character traits of people

    oai_token-act-pair · gemini-2.0-flash

    mean

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.73
    qvarna
    -0.47
     Privy
    -0.45
     NgModule
    -0.45
    รรม
    -0.43
    PLE
    -0.42
    ActionCreators
    -0.42
     estekak
    -0.42
    FFE
    -0.41
     урна
    -0.41
    POSITIVE LOGITS
     mean
    2.41
     Mean
    2.09
    mean
    2.06
    Mean
    1.90
     MEAN
    1.88
    MEAN
    1.66
     Means
    1.02
    means
    1.00
     MEANS
    0.99
    Means
    0.95
    Activations Density 2.776%

    No Known Activations